Subgraph Neural Networks
Subgraph Neural Networks
复制标题
DOI：
--
复制
发表时间：
2020-06
期刊：
影响因子：
--
通讯作者：
Emily Alsentzer;S. G. Finlayson;Michelle M. Li;M. Zitnik
中科院分区：
文献类型：
--
作者：
Emily Alsentzer;S. G. Finlayson;Michelle M. Li;M. Zitnik
图的深度学习方法在许多节点级和图级预测任务上都取得了显著的性能。然而，尽管这些方法的扩散及其成功，但流行的图神经网络（GNN）忽略了子图，使得子图预测任务在许多有影响力的应用中难以解决。此外，子图预测任务提出了几个独特的挑战，因为子图可以具有非平凡的内部拓扑，但也携带相对于它们存在的底层图的位置和外部连接信息的概念。在这里，我们介绍了SUB-GNN，一个子图神经网络来学习解纠缠子图表示。特别是，我们提出了一种新的子图路由机制，传播子图的组件和随机采样的锚补丁从底层图之间的神经消息，产生高度准确的子图表示。SUB-GNN指定了三个通道，每个通道都旨在捕获子图结构的一个不同方面，我们提供了经验证据，这些通道编码了它们的预期属性。我们设计了一系列新的合成和真实世界的子图数据集。在八个数据集上进行子图分类的实证结果表明，SUB-GNN实现了相当大的性能提升，比强基线方法（包括节点级和图级GNN）的性能高出12.4%。SUB-GNN在具有挑战性的生物医学数据集上表现得非常好，当子图具有复杂的拓扑结构，甚至包括多个不连接的组件时。
Deep learning methods for graphs achieve remarkable performance on many node-level and graph-level prediction tasks. However, despite the proliferation of the methods and their success, prevailing Graph Neural Networks (GNNs) neglect subgraphs, rendering subgraph prediction tasks challenging to tackle in many impactful applications. Further, subgraph prediction tasks present several unique challenges, because subgraphs can have non-trivial internal topology, but also carry a notion of position and external connectivity information relative to the underlying graph in which they exist. Here, we introduce SUB-GNN, a subgraph neural network to learn disentangled subgraph representations. In particular, we propose a novel subgraph routing mechanism that propagates neural messages between the subgraph's components and randomly sampled anchor patches from the underlying graph, yielding highly accurate subgraph representations. SUB-GNN specifies three channels, each designed to capture a distinct aspect of subgraph structure, and we provide empirical evidence that the channels encode their intended properties. We design a series of new synthetic and real-world subgraph datasets. Empirical results for subgraph classification on eight datasets show that SUB-GNN achieves considerable performance gains, outperforming strong baseline methods, including node-level and graph-level GNNs, by 12.4% over the strongest baseline. SUB-GNN performs exceptionally well on challenging biomedical datasets when subgraphs have complex topology and even comprise multiple disconnected components.